English
Related papers

Related papers: Misalignment from Treating Means as Ends

200 papers

It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people…

Artificial Intelligence · Computer Science 2019-07-02 Smitha Milli , Anca D. Dragan

Generative Adversarial Imitation Learning suffers from the fundamental problem of reward bias stemming from the choice of reward functions used in the algorithm. Different types of biases also affect different types of environments - which…

Machine Learning · Computer Science 2020-09-22 Rohit Jena , Siddharth Agrawal , Katia Sycara

In reinforcement learning, we often define goals by specifying rewards within desirable states. One problem with this approach is that we typically need to redefine the rewards each time the goal changes, which often requires some…

Artificial Intelligence · Computer Science 2017-07-26 Ashley D. Edwards , Srijan Sood , Charles L. Isbell

Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment…

Machine Learning · Computer Science 2017-03-10 Evan Shelhamer , Parsa Mahmoudieh , Max Argus , Trevor Darrell

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

Machine Learning · Computer Science 2025-04-29 Muhammad Qasim Elahi , Somtochukwu Oguchienti , Maheed H. Ahmed , Mahsa Ghasemi

The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical dilemma inherent in this training paradigm is the imbalanced…

Machine Learning · Computer Science 2026-05-27 Yu Huang , Zihua Zhao , Zhaoxin Huan , Wanli Gu , Feng Hong , Xinmu Ge , Lin Yuan , Weichang Wu , Qiang Hu , Xiaolu Zhang , Jun Zhou , Jiangchao Yao

Reinforcement learning problems are often described through rewards that indicate if an agent has completed some task. This specification can yield desirable behavior, however many problems are difficult to specify in this manner, as one…

Artificial Intelligence · Computer Science 2016-08-15 Ashley Edwards , Charles Isbell , Atsuo Takanishi

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

Machine Learning · Computer Science 2022-01-10 Weichao Zhou , Wenchao Li

A key challenge in reinforcement learning (RL) is reward (mis)specification, whereby imprecisely defined reward functions can result in unintended, possibly harmful, behaviours. Indeed, reward functions in RL are typically treated as…

Machine Learning · Computer Science 2025-10-22 Daniel Donnelly , Angelo Ferrando , Francesco Belardinelli

The success of reinforcement learning (RL) is fundamentally tied to having a reward function that accurately reflects the task objective. Yet, designing reward functions is notoriously time-consuming and prone to misspecification. To…

Machine Learning · Computer Science 2026-01-26 Calarina Muslimani , Yunshu Du , Kenta Kawamoto , Kaushik Subramanian , Peter Stone , Peter Wurman

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments,…

Computation and Language · Computer Science 2020-01-10 Daniel M. Ziegler , Nisan Stiennon , Jeffrey Wu , Tom B. Brown , Alec Radford , Dario Amodei , Paul Christiano , Geoffrey Irving

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Machine Learning · Computer Science 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

Humanoid control often leverages motion priors from human demonstrations to encourage natural behaviors. However, such demonstrations are frequently suboptimal or misaligned with robotic tasks due to embodiment differences, retargeting…

Robotics · Computer Science 2026-02-04 Ziang Zheng , Kai Feng , Yi Nie , Shentao Qin

We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g.,…

Robotics · Computer Science 2024-08-13 Connor Mattson , Anurag Aribandi , Daniel S. Brown

We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong…

Machine Learning · Computer Science 2023-01-11 Lauro Langosco , Jack Koch , Lee Sharkey , Jacob Pfau , Laurent Orseau , David Krueger

Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change the state of its environment. If that change precludes…

Artificial Intelligence · Computer Science 2020-06-11 Alexander Matt Turner , Dylan Hadfield-Menell , Prasad Tadepalli

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in…

Model-based reinforcement learning (MBRL) has been shown to be a powerful framework for data-efficiently learning control of continuous tasks. Recent work in MBRL has mostly focused on using more advanced function approximators and planning…

Machine Learning · Computer Science 2021-04-20 Nathan Lambert , Brandon Amos , Omry Yadan , Roberto Calandra